library(tidyverse)

main_csv <-"~/analysis_data/092925_unified_phab.csv"
main_df <- read.csv(main_csv, header = TRUE) 

set.seed(123) # For reproducibility

sampled_df <- main_df %>%
  group_by(source) %>%
  mutate(sampled_TaskPHID = TaskPHID %in% sample(unique(TaskPHID), 30)) %>%
  ungroup() %>%
  filter(sampled_TaskPHID) %>%
  select(-sampled_TaskPHID) 

sentence_level_sample <- sampled_df |>
  mutate(cleaned_sentences = str_extract_all(olmo_cleaned_sentences, "(?<=')[^']+(?=')")) |>
  unnest(cleaned_sentences)|>
  filter(cleaned_sentences != ", ") |>
  select(-olmo_sentence_categories, -starts_with("normalized"), -starts_with("gerrit"))

(nrow(sentence_level_sample) / 293) * 1.5

#write.csv(output_df, "100125_human_info_sample.csv", row.names = FALSE)